Healthcare
21 columns
200 rows
8 formats

Healthcare Billing Error Patterns

This dataset contains synthetic healthcare billing claims with embedded errors and anomalies, including detailed patient, provider, service, and audit information. It is ideal for developing, testing, and benchmarking claims auditing processes and machine learning models for error detection and process automation in healthcare billing.

last updated 29 Jul 2025
by GoMask

The brief that made it

Training and evaluating machine learning models for billing error and anomaly detection

Sample rows

preview · 8 of 200 rows · all 21 columns

claim_idstring	audit_outcomestring	billed_amountfloat	audit_flagboolean	insurance_planstring	patient_idstring	provider_idstring	service_datedate	billing_datedate	procedure_codestring	diagnosis_codestring	paid_amountfloat	claim_statusstring	error_flagboolean	error_typestring	created_atdatetime	updated_atdatetime	patient_dobdate	patient_genderstring	provider_specialtystring	error_descriptionstring
CLM000001	not_audited	142.5	false	PPO_PLUS	PAT001	PROV100	2022-04-12	2022-04-13	99213	J06.9	128.25	approved	false	blank	2022-04-13T10:04:33	2022-04-14T09:59:14	1981-10-15	female	internal medicine	blank
CLM000002	not_audited	49	false	SCHOOL_CHILD	PAT002	PROV101	2023-10-19	2023-10-25	36415	R79.1	49	approved	false	blank	2023-10-26T13:10:11	2023-10-27T08:23:57	2011-02-02	male	pediatrics	blank
CLM000003	not_audited	255	false	PPO_BASIC	PAT003	PROV102	2021-01-30	2021-02-01	93000	I48.91	229.5	approved	false	blank	2021-02-01T11:55:22	2021-02-03T10:10:08	1992-05-21	other	cardiology	blank
CLM000004	not_audited	193	false	HMO_BASIC_01	PAT004	PROV103	2020-08-18	2020-08-19	99395	Z00.00	184.5	pending	false	blank	2020-08-20T12:18:19	2020-08-22T08:19:56	1988-09-09	female	primary care	blank
CLM000005	passed	1800	true	ACA_GOLD	PAT005	PROV104	2019-11-06	2019-11-08	70450	S06.0X0A	1530	approved	false	blank	2019-11-09T10:18:20	2019-11-10T12:21:08	1957-03-14	male	radiology	blank
CLM000006	failed	88	true	HMO_SMOKECARE	PAT006	PROV105	2023-06-15	2023-06-21	96372	E11.9	70.4	denied	true	missing info	2023-06-22T09:17:31	2023-06-24T11:22:44	1997-12-30	male	nursing	Patient insurance number missing from submitted claim form.
CLM000007	not_audited	190	false	VIP_EXECUTIVE	PAT002	PROV100	2021-05-23	2021-05-24	90791	F41.1	173.8	approved	false	blank	2021-05-25T10:14:07	2021-05-26T09:08:12	1987-05-16	male	psychiatry	blank
CLM000008	not_audited	75	false	MEDICAID_CHILD	PAT007	PROV106	2022-12-12	2022-12-13	93010	R07.9	75	approved	false	blank	2022-12-14T13:42:55	2022-12-16T08:50:19	2017-03-25	female	student health	blank
CLM000009	not_audited	201	false	UNIVERSITY_CARE	PAT008	PROV107	2021-03-21	2021-03-22	99396	Z00.01	193	approved	false	blank	2021-03-23T14:17:49	2021-03-25T09:33:27	2007-07-10	female	pediatrics	blank
CLM000010	not_audited	42	false	HMO_SMOKECARE	PAT009	PROV108	2020-10-29	2020-10-29	99406	F17.210	42	approved	false	blank	2020-10-29T16:31:15	2020-10-30T09:58:26	1995-03-05	female	pulmonology	blank
CLM000011	passed	92	true	VIP_EXECUTIVE	PAT010	PROV109	2018-09-18	2018-09-20	80053	E78.5	83.7	approved	false	blank	2018-09-21T12:14:00	2018-09-22T10:16:18	1975-11-22	male	endocrinology	blank
CLM000012	not_audited	184	false	PPO_PLUS	PAT011	PROV104	2022-03-03	2022-03-05	99214	R51	165.6	approved	false	blank	2022-03-06T14:00:11	2022-03-07T11:01:32	1986-07-18	male	family medicine	blank
CLM000013	not_audited	27	false	MEDICAID_CHILD	PAT012	PROV110	2023-03-12	2023-03-13	36415	R79.1	27	approved	false	blank	2023-03-14T13:42:22	2023-03-15T10:18:40	2015-09-06	female	phlebotomy	blank
CLM000014	not_audited	132.5	false	PPO_PLUS	PAT013	PROV111	2020-02-20	2020-02-21	99203	M54.5	119.25	pending	false	blank	2020-02-22T11:28:34	2020-02-24T17:37:22	1990-02-14	female	primary care	blank
CLM000015	passed	350	true	PPO_BASIC	PAT014	PROV112	2021-11-11	2021-11-13	99285	J44.1	315	approved	false	blank	2021-11-14T15:12:27	2021-11-16T08:20:14	1970-08-07	male	emergency medicine	blank
CLM000016	failed	55	true	HMO_SMOKECARE	PAT015	PROV113	2022-08-17	2022-08-18	99406	F17.210	0	denied	true	duplicate	2022-08-19T17:01:33	2022-08-20T14:21:45	1979-11-29	male	nursing	Duplicate claim detected for same patient and procedure within billing period.
CLM000017	not_audited	105	false	PPO_PLUS	PAT016	PROV114	2020-06-16	2020-06-18	80061	E78.0	89.25	submitted	false	blank	2020-06-18T10:11:09	2020-06-19T09:27:31	1984-02-02	female	endocrinology	blank
CLM000018	passed	218	true	VIP_EXECUTIVE	PAT017	PROV115	2019-05-05	2019-05-07	99223	I10	196.2	approved	false	blank	2019-05-08T15:34:17	2019-05-09T11:06:15	1951-01-26	male	internal medicine	blank
CLM000019	not_audited	38	false	MEDICAID_CHILD	PAT018	PROV116	2022-07-08	2022-07-14	81001	N39.0	38	approved	false	blank	2022-07-14T11:55:10	2022-07-15T10:20:14	2010-04-18	other	allergy & immunology	blank
CLM000020	not_audited	435	false	ACA_GOLD	PAT019	PROV117	2021-02-02	2021-02-03	99284	J45.909	391.5	approved	false	blank	2021-02-04T10:41:17	2021-02-06T09:18:41	1982-12-12	female	emergency medicine	blank

What the 200 rows show

from the 200-row sample

Passed (audit outcome) stands out: 46 of its 46 rows have audit_flag = true, against 15 of 149 for the rest.

31%audit_flag = true
175.0median billed_amount
4error types
4patient genders
5claim statuses
33provider specialties

Audit flag rate by audit_outcomeaudit_flag = true

Passed (audit outcome)'s mean billed_amount is 4,343, against 118.0 for failed, 156.0 for corrected and 183.9 for not_audited.

billed_amount195 rows, in bands of 5,000

Median 175.0, from 27.0 to 48,000.

insurance_plan195 rows with a value · 5 left blank

PPO_PLUS38
HMO_BASIC_0124
PPO_BASIC20
VIP_EXECUTIVE20
EMPLOYEE_HR_2217
ACA_GOLD16
HMO_SMOKECARE15
SCHOOL_CHILD9
UNIVERSITY_CARE8
ONCOLOGIC_SPECIAL7

21 columns by typefrom the column list below

string 12
float 2
date 3
datetime 2
boolean 2

Columns

21 columns in four groups

blueprint · 21 columns
column	type	description	example
Text 12 columns
`claim_id`	string	Unique identifier for each billing claim record.unique	CLM000001
`patient_id`	string	Unique identifier for the patient associated with the claim.	PAT001
`provider_id`	string	Unique identifier for the healthcare provider submitting the claim.	PROV100
`procedure_code`	string	Standardized code representing the medical procedure performed (e.g., CPT or ICD code).	99213
`diagnosis_code`	string	Standardized code representing the patient's diagnosis.	J06.9
`insurance_plan`	string	Name or code of the insurance plan covering the claim.	PPO_PLUS
`claim_status`	string	Current status of the claim (e.g., submitted, approved, denied, pending, corrected).submitted · approved · denied · pending · corrected	approved
`error_type`	string	Type or category of error present in the claim, if any (e.g., upcoding, duplicate, missing info, unbundling, none).4 types · optional	missing info
`error_description`	string	Detailed description of the error or anomaly in the claim, if applicable.optional	Patient insurance number …
`audit_outcome`	string	Result of the audit process (e.g., passed, failed, corrected, not_audited).passed · failed · corrected · not_audited · optional	not_audited
`patient_gender`	string	Gender of the patient.male · female · other · unknown · optional	female
`provider_specialty`	string	Medical specialty of the provider submitting the claim.optional	internal medicine
Numbers 2 columns
`billed_amount`	float	Total amount billed for the claim.0 or more	142.5
`paid_amount`	float	Amount paid by the insurer for the claim.0 or more	128.25
Dates and times 5 columns
`service_date`	date	Date when the healthcare service was provided.	2022-04-12
`billing_date`	date	Date when the billing claim was submitted.	2022-04-13
`created_at`	datetime	Timestamp when the claim record was created in the system.	2022-04-13T10:04:33
`updated_at`	datetime	Timestamp when the claim record was last updated.	2022-04-14T09:59:14
`patient_dob`	date	Date of birth of the patient.optional	1981-10-15
True or false 2 columns
`error_flag`	boolean	Indicates whether the claim contains a known error or anomaly.	false
`audit_flag`	boolean	Indicates if the claim was selected for audit.	false

Use it for

A healthcare dashboard
The audit_flag rate, billed_amount by audit_outcome and a breakdown of insurance_plan. Excel, Power BI or Tableau.
Why do 61 of 195 rows have audit_flag = true?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Claims200
CLM000001142.5not_audi…
CLM0000051800passed
CLM00000688failed
A software demo
Believable claims with patient_id, provider_id and service_date to fill a screen in front of a buyer.

This dataset200 rows21 columns

Yours1,000 rows21 columns

blueprint · healthcare-billing-error-patterns

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 21 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.

Rules it was built with

Claims have unique patient and provider IDs
Common billing codes used per diagnosis
Upcoding and duplicate charges simulated
Denied claims flagged with reasons

Rows1,000 rows10,000 rows100,000 rows1,000,000 rows

Open the blueprint in Data Factory

1 credit per row. Preview 20 rows free. Buy rows for the full run.

Exports: CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence: yours to use, including commercially
API slug: healthcare-billing-error-patterns

What should your data show?

No signup. No card.

Sample rows

What the 200 rows show

Columns

Use it for

A healthcare dashboard

A root-cause class exercise

A software demo

Make it yours.

Same schema. As many rows as you need.

More in Healthcare

What should your data show?